INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ITE

-0.16

oward

-0.16

kara

-0.15

edin

-0.15

wayne

-0.15

edi

-0.15

halb

-0.14

wards

-0.14

edar

-0.14

eden

-0.14

POSITIVE LOGITS

 bear

0.23

bear

0.19

usat

0.14

bie

0.14

earer

0.14

 fruition

0.14

çĦ

0.14

 awareness

0.14

ignum

0.14

emean

0.13

Activations Density 0.024%

No Comments

No Known Activations